© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119957
    Prev
    Next
    INDEX
    Explanations

    told me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -1.53
    m
    -1.41
    I
    -1.39
    stappen
    -1.38
     When
    -1.30
     Pastikan
    -1.28
     new
    -1.28
    e
    -1.27
    er
    -1.20
     Terbaru
    -1.20
    POSITIVE LOGITS
    鹩
    1.68
    
    1.66
     of
    1.63
    
    1.63
     to
    1.55
    盉
    1.54
    蛱
    1.48
    鹋
    1.45
    仅
    1.44
     poroz
    1.42
    Activations Density 0.047%

    No Known Activations